# Learning to Score

arXiv: https://arxiv.org/abs/2504.14302 · HTML: https://mlsanity.com/paper/2504.14302/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 7 of its 21 references that are in the map.
- First posted on arXiv 19 Apr 2025.

## Builds on (most cited first, 7 of 7)

- [Deep Variational Information Bottleneck](https://mlsanity.com/paper/1612.00410/) (2016)
- [Deep metric learning using Triplet network](https://mlsanity.com/paper/1412.6622/) (2014)
- [Learning Robust Representations via Multi-View Information Bottleneck](https://mlsanity.com/paper/2002.07017/) (2020)
- [Unsupervised and Semi-supervised Learning with Categorical Generative Adversarial Networks](https://mlsanity.com/paper/1511.06390/) (2015)
- [Constraining Variational Inference with Geometric Jensen-Shannon Divergence](https://mlsanity.com/paper/2006.10599/) (2020)
- [Patterns for Learning with Side Information](https://mlsanity.com/paper/1511.06429/) (2015)
- [HAVANA: Hierarchical and Variation-Normalized Autoencoder for Person Re-identification](https://mlsanity.com/paper/2101.02568/) (2021)

## Abstract (arXiv)

Common machine learning settings range from supervised tasks, where accurately labeled data is accessible, through semi-supervised and weakly-supervised tasks, where target labels are scant or noisy, to unsupervised tasks where labels are unobtainable. In this paper we study a scenario where the target labels are not available but additional related information is at hand. This information, referred to as Side Information, is either correlated with the unknown labels or imposes constraints on the feature space. We formulate the problem as an ensemble of three semantic components: representation learning, side information and metric learning. The proposed scoring model is advantageous for multiple use-cases. For example, in the healthcare domain it can be used to create a severity score for diseases where the symptoms are known but the criteria for the disease progression are not well defined. We demonstrate the utility of the suggested scoring system on well-known benchmark data-sets and bio-medical patient records.